Machine Learning as a Diagnostic and Prognostic Tool for Predicting Thrombosis in Cancer Patients: A Systematic Review.

Khorana score (KS) is an established risk assessment model for predicting cancer-associated thrombosis. However, it ignores several risk factors and has poor predictability in some cancer types. Machine learning (ML) is a novel technique used for the diagnosis and prognosis of several diseases, including cancer-associated thrombosis, when trained on specific diagnostic modalities. Consolidating the literature on the use of ML for the prediction of cancer-associated thrombosis is necessary to understand its diagnostic and prognostic abilities relative to KS. This systematic review aims to evaluate the current use and performance of ML algorithms to predict thrombosis in cancer patients. This study was conducted per Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. Databases Medline, EMBASE, Cochrane, and ClinicalTrials.gov, were searched from inception to September 15, 2023, for studies evaluating the use of ML models for the prediction of thrombosis in cancer patients. Search terms "machine learning," "artificial intelligence," "thrombosis," and "cancer" were used. Studies that examined adult cancer patients using any ML model were included. Two independent reviewers conducted study selection and data extraction. Three hundred citations were screened, of which 29 studies underwent a full-text review, and ultimately, 8 studies with 22,893 patients were included. Sample sizes ranged from 348 to 16,407 patients. Thrombosis was characterized as venous thromboembolism (n = 6) or peripherally inserted central catheter thrombosis (n = 2). The types of cancer included breast, gastric, colorectal, bladder, lung, esophageal, pancreatic, biliary, prostate, ovarian, genitourinary, head-neck, and sarcoma. All studies reported outcomes on the ML's predictive capacity. The extreme gradient boosting appears to be the best-performing model, and several models outperform KS in their respective datasets.

Sex differences in the outcomes after transcatheter aortic valve replacement with newer generation devices: A meta-analysis.

BACKGROUND: Transcatheter aortic valve replacement (TAVR) is a reasonable therapeutic approach among patients with symptomatic severe aortic stenosis irrespective of surgical risk. Data regarding sex-specific differences in the outcomes with newer generation valves are limited. METHODS: Electronic databases were searched for studies assessing sex differences in the outcomes of patients undergoing TAVR with newer generation valves (SAPIEN 3 or Evolut). Random effects model was constructed for summary estimates. RESULTS: Four observational studies with 4522 patients (44.8% women) were included in the meta-analysis. Women were older and had a lower prevalence of coronary artery disease and mean EuroScore. Women had a higher incidence of short-term mortality (up to 30 days) (risk ratio [RR]: 1.60, 95% confidence interval [CI]: 1.14-2.25), but no difference in 1-year mortality (RR: 0.92, 95% CI: 0.72-1.17). There was no significant difference in the incidence of major bleeding (RR: 1.16, 95% CI: 0.86-1.57), permanent pacemaker (PPM) (RR: 0.80, 95% CI: 0.62-1.04), or disabling stroke (RR: 1.16, 95% CI: 0.54-2.45). CONCLUSION: In this meta-analysis, we found that women undergoing TAVR with newer-generation devices were older but had a lower prevalence of comorbidities. Women had a higher incidence of short-term mortality but no difference in the 1-year mortality, bleeding, PPM, or stroke compared with men. Future studies are required to confirm these findings.

ABO Blood Group and the Risk of Thrombosis in Cancer Patients: A Mini-Review.

Cancer-associated thrombosis (CT), especially venous thromboembolism (VTE), is a common occurrence with several factors contributing to a wide diversity in thrombosis risk. The association between ABO blood groups and the risk for CT has been examined in various studies, with non-O blood type associated with an increased thrombosis risk; however, these studies have reported varying results with recognized limitations. ABO blood groups are known to be implicated in hemostasis, in an association mediated through von Willebrand factor (VWF). In this narrative review, we aim to summarize the current knowledge surrounding the role of ABO blood groups in VTE, with a particular focus on the role of VWF and other contributing risk factors on VTE occurrence. We found evidence from literature for the impact of ABO blood groups in determining the risk of VTE in healthy populations, with a limited number of studies examining this effect in cancer patients. Additionally, research on the impact of ABO on different cancer types lacks rigor, particularly in regard to other risk factors. Overall, most studies showed strong association of increased risk of VTE amongst cancer patients with non-O blood groups and increased VWF levels. This association was weaker in a few studies. Further research is needed before a solid conclusion can be made about the ABO or ABO-VWF-mediated hypercoagulability and VTE risk in various cancers. These studies will help determine if ABO typing can be an added biomarker to improve VTE risk assessment models in cancer patients.

COVID-19 Vaccine-Associated Immune Thrombosis and Thrombocytopenia (VITT): Diagnostic Discrepancies and Global Implications.

Vaccine-induced immune thrombotic thrombocytopenia (VITT) has been reported in association with the coronavirus disease 2019 preventative adenovirus vector-based vaccines ChAdOx1 nCoV-19 (Oxford/AstraZeneca) and Ad26.COV2.S (Janssen/Johnson & Johnson) in hundreds of recipients across the globe. VITT is characterized by thrombosis, typically at unusual sites, low fibrinogen, and elevated plasma D-dimer, generally manifesting between 4 and 28 days following vaccination. Detection of anti-platelet factor antibodies using an enzyme-linked immunosorbent assay (ELISA) is often confirmatory. Although several similar principles subside in most diagnostic criteria for VITT, the presentation of a positive ELISA assay, use of expert hematology and neurology opinion, and exclusion of possible VITT cases outside the "standard" 4 to 28-day timeframe have contributed a lack of global standardization for defining VITT. Accordingly, the global and regional incidence of VITT differs according to the diagnostic pathway and case definition used. This has influenced the public perception of VITT's severity and the decision to use adenovirus vector-based vaccines for limiting severe acute respiratory syndrome coronavirus 2 infection. We hereby delineate the recognized pathogenic mechanisms, global incidence, discrepancies in diagnostic criteria, recommended treatments, and global implications to vaccine hesitancy from this coagulopathy.